3D cephalometric landmark detection by multiple stage deep reinforcement learning
Abstract The lengthy time needed for manual landmarking has delayed the widespread adoption of three-dimensional (3D) cephalometry. We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging. This system consider...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/14c3583b99004793a05cc73915f23c71 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:14c3583b99004793a05cc73915f23c71 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:14c3583b99004793a05cc73915f23c712021-12-02T15:28:57Z3D cephalometric landmark detection by multiple stage deep reinforcement learning10.1038/s41598-021-97116-72045-2322https://doaj.org/article/14c3583b99004793a05cc73915f23c712021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97116-7https://doaj.org/toc/2045-2322Abstract The lengthy time needed for manual landmarking has delayed the widespread adoption of three-dimensional (3D) cephalometry. We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging. This system considers geometrical characteristics of landmarks and simulates the sequential decision process underlying human professional landmarking patterns. It consists mainly of constructing an appropriate two-dimensional cutaway or 3D model view, then implementing single-stage DRL with gradient-based boundary estimation or multi-stage DRL to dictate the 3D coordinates of target landmarks. This system clearly shows sufficient detection accuracy and stability for direct clinical applications, with a low level of detection error and low inter-individual variation (1.96 ± 0.78 mm). Our system, moreover, requires no additional steps of segmentation and 3D mesh-object construction for landmark detection. We believe these system features will enable fast-track cephalometric analysis and planning and expect it to achieve greater accuracy as larger CT datasets become available for training and testing.Sung Ho KangKiwan JeonSang-Hoon KangSang-Hwy LeeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Sung Ho Kang Kiwan Jeon Sang-Hoon Kang Sang-Hwy Lee 3D cephalometric landmark detection by multiple stage deep reinforcement learning |
description |
Abstract The lengthy time needed for manual landmarking has delayed the widespread adoption of three-dimensional (3D) cephalometry. We here propose an automatic 3D cephalometric annotation system based on multi-stage deep reinforcement learning (DRL) and volume-rendered imaging. This system considers geometrical characteristics of landmarks and simulates the sequential decision process underlying human professional landmarking patterns. It consists mainly of constructing an appropriate two-dimensional cutaway or 3D model view, then implementing single-stage DRL with gradient-based boundary estimation or multi-stage DRL to dictate the 3D coordinates of target landmarks. This system clearly shows sufficient detection accuracy and stability for direct clinical applications, with a low level of detection error and low inter-individual variation (1.96 ± 0.78 mm). Our system, moreover, requires no additional steps of segmentation and 3D mesh-object construction for landmark detection. We believe these system features will enable fast-track cephalometric analysis and planning and expect it to achieve greater accuracy as larger CT datasets become available for training and testing. |
format |
article |
author |
Sung Ho Kang Kiwan Jeon Sang-Hoon Kang Sang-Hwy Lee |
author_facet |
Sung Ho Kang Kiwan Jeon Sang-Hoon Kang Sang-Hwy Lee |
author_sort |
Sung Ho Kang |
title |
3D cephalometric landmark detection by multiple stage deep reinforcement learning |
title_short |
3D cephalometric landmark detection by multiple stage deep reinforcement learning |
title_full |
3D cephalometric landmark detection by multiple stage deep reinforcement learning |
title_fullStr |
3D cephalometric landmark detection by multiple stage deep reinforcement learning |
title_full_unstemmed |
3D cephalometric landmark detection by multiple stage deep reinforcement learning |
title_sort |
3d cephalometric landmark detection by multiple stage deep reinforcement learning |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/14c3583b99004793a05cc73915f23c71 |
work_keys_str_mv |
AT sunghokang 3dcephalometriclandmarkdetectionbymultiplestagedeepreinforcementlearning AT kiwanjeon 3dcephalometriclandmarkdetectionbymultiplestagedeepreinforcementlearning AT sanghoonkang 3dcephalometriclandmarkdetectionbymultiplestagedeepreinforcementlearning AT sanghwylee 3dcephalometriclandmarkdetectionbymultiplestagedeepreinforcementlearning |
_version_ |
1718387187165167616 |